qurator-spk/sbb_binarization
1
0
Fork 0
mirror of https://github.com/qurator-spk/sbb_binarization.git synced 2025-07-11 11:59:53 +02:00
Code Issues Releases Wiki Activity

image_from_segment: exclude already binarized images

Browse source 
Co-authored-by: Robert Sachunsky <38561704+bertsky@users.noreply.github.com>
This commit is contained in:
Konstantin Baierer 2020-10-16 10:59:42 +02:00 • committed by GitHub
parent 12b44af329
commit 0650bad533
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
sbb_binarize/ocrd_cli.py
View file

@ -73,7 +73,7 @@ class SbbBinarizeProcessor(Processor):
if oplevel == 'page': if oplevel == 'page':
LOG.info("Binarizing on 'page' level in page '%s'", page_id) LOG.info("Binarizing on 'page' level in page '%s'", page_id)
page_image, page_xywh, _ = self.workspace.image_from_page(page, page_id) page_image, page_xywh, _ = self.workspace.image_from_page(page, page_id, feature_filter='binarized')
bin_image = self._run_binarizer(page_image) bin_image = self._run_binarizer(page_image)
# update METS (add the image file): # update METS (add the image file):
bin_image_path = self.workspace.save_image_file(bin_image, bin_image_path = self.workspace.save_image_file(bin_image,
@ -88,7 +88,7 @@ class SbbBinarizeProcessor(Processor):
LOG.warning("Page '%s' contains no text/table regions", page_id) LOG.warning("Page '%s' contains no text/table regions", page_id)
for region in regions: for region in regions:
region_image, region_xywh = self.workspace.image_from_segment(region, page_image, page_xywh) region_image, region_xywh = self.workspace.image_from_segment(region, page_image, page_xywh, feature_filter='binarized')
if oplevel == 'region': if oplevel == 'region':
region_image_bin = self._run_binarizer(region_image) region_image_bin = self._run_binarizer(region_image)
@ -105,7 +105,7 @@ class SbbBinarizeProcessor(Processor):
if not lines: if not lines:
LOG.warning("Page '%s' region '%s' contains no text lines", page_id, region.id) LOG.warning("Page '%s' region '%s' contains no text lines", page_id, region.id)
for line in lines: for line in lines:
line_image, line_xywh = self.workspace.image_from_segment(line, page_image, page_xywh) line_image, line_xywh = self.workspace.image_from_segment(line, page_image, page_xywh, feature_filter='binarized')
line_image_bin = self._run_binarizer(line_image) line_image_bin = self._run_binarizer(line_image)
line_image_bin_path = self.workspace.save_image_file( line_image_bin_path = self.workspace.save_image_file(
line_image_bin, line_image_bin,